© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1914
    Prev
    Next
    INDEX
    Explanations

    concepts related to counterfactual reasoning and its implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "counter" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    counterfactual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NgModule
    -0.75
     AssemblyCulture
    -0.74
    Portail
    -0.72
    tagHelperRunner
    -0.65
     ComVisible
    -0.62
    URLException
    -0.62
     smtplib
    -0.57
    wsgi
    -0.55
    にほんブログ村
    -0.55
     fédé
    -0.55
    POSITIVE LOGITS
     Counter
    1.40
     counter
    1.36
     COUNTER
    1.29
    Counter
    1.18
     counters
    1.17
    counter
    1.14
    COUNTER
    1.05
     Counters
    1.04
    counters
    0.90
    Counters
    0.90
    Activations Density 0.063%

    No Known Activations